<![CDATA[Mental health is an important aspect of human life. Depression, anxiety and stress are some of the most common mental health disorders. These disorders can negatively impact daily life, including productivity, social relationships, and an individual's quality of life, requiring accurate prediction for early intervention. One of the psychological measurement tools used to assess a person's level of depression, anxiety, and stress is the DASS-42 (Depression Anxiety Stress Scales - Long Form). In addition to the DASS-42 results, demographic factors such as age, gender, education level, and social status are important to analyze to strengthen the analysis. Machine learning (ML) is a powerful tool for analyzing complex data such as predicting psychological demographic factors associated with these mental health conditions. This study explores the potential of ML using a comprehensive dataset, using K-Nearest Neighbor and Support Vector Machine algorithms to assess prediction performance. The findings highlighted the effectiveness of ML models in predicting depression, anxiety and stress with high accuracy. The best algorithm in this study for the classification of depression, anxiety and stress is SVM with 99% accuracy but the use of Exploratory Data Analysis (EDA) technic to process additional variables affects the accuracy of the model so it can be concluded that demographic variables have an influence on the classification of depression, anxiety and stress.]]>
Copyrights © 2024
